11 Customer Success Challenges Inside One Resolution Loop
See how 11 Customer Success challenges break the path from customer signal to verified outcome, and where current CS tools still leave coordination work.
Bobb Kim
Bobb Kim is an engineer at Runbear, working on Slack-native AI teammates and applied AI workflows. He writes about practical ways teams can use AI agents to reduce manual work.
Engineer
Design in Claude Code. Keep It Running in Runbear.
Build and improve a Runbear agent from Claude Code, then keep the approved teammate connected to apps, triggers, Slack permissions, and run history for the whole team.
We moved our support playbook off one laptop
How Runbear turned one teammate's local CS skills into a shared, trigger-driven workflow with human decisions in Slack.
Runbear: The Slack AI Teammate That Resolves Support Issues, Not Just Replies
Support AI should not stop at explaining tickets. See how Runbear turns safe, repeatable fixes into Slack workflows with scoped permissions, approval, auto-resolve, and an audit trail.
We Won $1,000 in AI Credits. Then Lost It to Trial Abuse Over the Weekend
Free trial abuse is not stopped by detection alone. See how AI credit farming exposed the need for an operator workflow that can verify, escalate, block, and audit.
Your AI Can Read Your Docs — But Not Your Tables
Tables are the blind spot in RAG pipelines. We rebuilt how Notion and Confluence tables reach your LLM — from Markdown to self-describing header-value pairs — and improved answer accuracy by 20.6%.
Your Slack MCP Isn’t Broken — Your AI Just Can’t Read It
Connecting Slack to an AI agent is easy. Making that data actually useful to an LLM is the hard part. We improved retrieval accuracy by 27% with three changes: thread-level document splitting, noise filtering, and markup cleanup.